😊 Hi, this is Linfeng Feng from Guangdong, China, where it is known for its Cantonese pop, delicious cuisine, and humid climate.
I am currently working toward the Ph.D. degree in information and communication engineering with the Northwestern Polytechnical University, Xi’an, China. Concurrently, I am an intern with the Institute of Artificial Intelligence (TeleAI), China Telecom. My research interests include spatial audio, speech enhancement, and multimodal learning.

🏫 Educations

• 2024.03 - now, Ph.D. candidate in Information and Communication Engineer, Northwestern Polytechnical University, Xi’an, China.
• 2021.09 - 2024.03, M.S. in Information and Communication Engineer, Northwestern Polytechnical University, Xi’an, China.
• 2017.09 - 2021.06, B.S. in Communication Engineer, Guangdong Polytechnic Normal University, Guangzhou, China.

💻 Internships

• 2024.01 - now, Institute of Artificial Intelligence (TeleAI), China Telecom, China.

📝 Publications

2025

• AudioSpa: Spatializing Sound Events with Text [pdf] [demo]
  Linfeng Feng*, Lei Zhao*, Boyu Zhu, Xiao-Lei Zhang, Xuelong Li
  Preprint
• UniForm: A Unified Diffusion Transformer for Audio-Video Generation [pdf] [demo]
  Lei Zhao*, Linfeng Feng*, Dongxu Ge*, Fangqiu Yi, Chi Zhang, Xiao-Lei Zhang, Xuelong Li
  Preprint
• Co-Attention Based Multi-Channel TF-GridNet for Speech Separation with Ad-Hoc Microphone Arrays
  Hongmei Guo, Linfeng Feng, Yijiang Chen, Xueqing Li, Boyu Zhu, Hao-Yu Wang, Xiao-Lei Zhang, Xuelong Li
  Proceedings of the 49th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2025)

2024

• Quantization-error-free soft label for 2D sound source localization [pdf]
  Linfeng Feng, Xiao-Lei Zhang, and Xuelong Li
  Proceedings of 14th International Symposium on Chinese Spoken Language Processing (ISCSLP 2024)
• Learning Multi-dimensional Speaker Localization: Axis Partitioning, Unbiased Label Distribution, and Data Augmentation [pdf]
  Linfeng Feng, Yijun Gong, Zhi Liu, Xiao-Lei Zhang, and Xuelong Li
  IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE T-ASLP)
• Eliminating Quantization Errors in Classification-Based Sound Source Localization [pdf] [code]
  Linfeng Feng, Xiao-Lei Zhang, and Xuelong Li
  Neural Networks (NNJ)

2023

• Soft Label Coding for End-to-end Sound Source Localization with Ad-hoc Microphone Arrays [pdf]
  Linfeng Feng, Yijun Gong, and Xiao-Lei Zhang
  Proceedings of the 47th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2023)

🎖️ Competitions

• First place on ASR and third place on overall score, URGENT speech enhancement challenge of NeurIPS 2024 [Leaderboard]
  Linfeng Feng, Hao Ma, Haocheng Dong, Xiao-Lei Zhang, and Xuelong Li